ItemRAG: Item-Based Retrieval-Augmented Generation for LLM-Based Recommendation

TL;DR

ItemRAG introduces a fine-grained item-level retrieval method for LLM-based recommendation systems, combining co-purchase and semantic data to improve recommendation accuracy, especially for cold-start items.

Contribution

It proposes a novel item-level retrieval approach that enhances LLM recommendations by integrating co-purchase and semantic information, outperforming existing methods.

Findings

ItemRAG outperforms existing RAG approaches in standard and cold-start settings.

Combining co-purchase and semantic information improves retrieval relevance.

The approach benefits cold-start item recommendations.

Abstract

Recently, large language models (LLMs) have been widely used as recommender systems, owing to their reasoning capability and effectiveness in handling cold-start items. A common approach prompts an LLM with a target user's purchase history to recommend items from a candidate set, often enhanced with retrieval-augmented generation (RAG). Most existing RAG approaches retrieve purchase histories of users similar to the target user; however, these histories often contain noisy or weakly relevant information and provide little or no useful information for candidate items. To address these limitations, we propose ItemRAG, a novel RAG approach that shifts focus from coarse user-history retrieval to fine-grained item-level retrieval. ItemRAG augments the description of each item in the target user's history or the candidate set by retrieving items relevant to each. To retrieve items not merely semantically similar but informative for recommendation, ItemRAG leverages co-purchase information alongside semantic information. Especially, through their careful combination, ItemRAG prioritizes more informative retrievals and also benefits cold-start items. Through extensive experiments, we demonstrate that ItemRAG consistently outperforms existing RAG approaches under both standard and cold-start item recommendation settings. Supplementary materials, code, and datasets are provided at https://github.com/kswoo97/ItemRAG.